Active computerized pharmacovigilance using natural language processing, statistics, and electronic health records: a feasibility study

Abstract

OBJECTIVE It is vital to detect the full safety profile of a drug throughout its market life. Current pharmacovigilance systems still have substantial limitations, however. The objective of our work is to demonstrate the feasibility of using natural language processing (NLP), the comprehensive Electronic Health Record (EHR), and association statistics for pharmacovigilance purposes. DESIGN Narrative discharge summaries were collected from the Clinical Information System at New York Presbyterian Hospital (NYPH). MedLEE, an NLP system, was applied to the collection to identify medication events and entities which could be potential adverse drug events (ADEs). Co-occurrence statistics with adjusted volume tests were used to detect associations between the two types of entities, to calculate the strengths of the associations, and to determine their cutoff thresholds. Seven drugs/drug classes (ibuprofen, morphine, warfarin, bupropion, paroxetine, rosiglitazone, ACE inhibitors) with known ADEs were selected to evaluate the system. RESULTS One hundred thirty-two potential ADEs were found to be associated with the 7 drugs. Overall recall and precision were 0.75 and 0.31 for known ADEs respectively. Importantly, qualitative evaluation using historic roll back design suggested that novel ADEs could be detected using our system. CONCLUSIONS This study provides a framework for the development of active, high-throughput and prospective systems which could potentially unveil drug safety profiles throughout their entire market life. Our results demonstrate that the framework is feasible although there are some challenging issues. To the best of our knowledge, this is the first study using comprehensive unstructured data from the EHR for pharmacovigilance.

Figure 1

Example of simplified MedLEE output in XML format for the sentence She has recurring frontal headaches.

Figure 2

Overview of System Framework. The framework for detecting drug-ADE associations from narrative reports has five major phases: (1) data collection: collecting the set of reports to be mined; (2) data extraction: processing the reports using NLP to encode clinical entities; (3) data selection: selecting drug and possible ADE entities; (4) data filtering: excluding possible confounding information using two filters; and (5) statistical analysis: determining co-occurring drug-ADE candidates, and applying statistical methods to reveal associations between drugs and ADE candidates. The strength of associations were calculated and cutoffs were determined by co-occurence statistics adjusted by volume tests.